./outs

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [biodatlab/whisper-th-medium-combined](https://huggingface.co/biodatlab/whisper-th-medium-combined) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5637
-- Cer: 29.9814
+- Loss: 0.4437
+- Cer: 19.5098
 
 ## Model description
 
@@ -42,16 +42,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6.0
+- num_epochs: 3.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.3375        | 1.0   | 537  | 0.5168          | 24.9036 |
-| 0.2035        | 2.0   | 1074 | 0.5558          | 28.2356 |
-| 0.0809        | 3.0   | 1611 | 0.5637          | 29.9814 |
+| 0.3111        | 1.0   | 537  | 0.4584          | 46.2557 |
+| 0.1731        | 2.0   | 1074 | 0.4588          | 22.1901 |
+| 0.0347        | 3.0   | 1611 | 0.4437          | 19.5098 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f163cc930ff7ae702cf9db5ea3ecc7ca4d771e708a111ef0a7f6b5fe5eb37b0e
+oid sha256:230b1483b380cfe4fa7bee63f5be3383672443e729490396d68ae0b047e2f0a7
 size 3055544304

runs/Oct08_23-09-15_da57771655df/events.out.tfevents.1728428959.da57771655df.1010.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19a3dad623c5c94ad7f0cba850b15bcac5aec74e2118ae2f0f5156f63ae66ad
+size 10372

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fd56e536c7d72531cae2b80ea823836ac51b338b4a62138a2a3494649243a4
+oid sha256:e3b7c5b251ba029f3b2a3e8cade9e16a0ab1208839350c07d6b25b69eb862909
 size 5304